Can I use models other than Claude?

Yes, the system's ModelFactory provides a unified interface for Claude, OpenAI, DeepSeek, Groq, Gemini, and Ollama.

How does the system handle trading risk?

A dedicated Risk Agent runs before trading decisions are executed, checking parameters like MAX_LOSS_USD, position sizing, and account balance.

Which exchanges does this skill support?

It currently supports Hyperliquid (perpetuals), Solana/BirdEye (spot), and Extended Exchange (X10).

What is the Research-Based Inference (RBI) agent?

The RBI agent uses LLMs to extract trading logic from external sources like YouTube videos or PDFs and automatically generates backtesting.py compatible code.

What is the primary development philosophy of this system?

The system follows a 'never over-engineer' approach, keeping agents under 800 lines and favoring modular, standalone executables over complex hierarchies.

Moon Dev AI Trading Agents

Name: Moon Dev AI Trading Agents
Author: Microck

byMicrock

•

Ciencia de Datos y ML

Orchestrates a fleet of 48+ specialized AI agents for autonomous cryptocurrency trading, market analysis, and strategy backtesting.

This skill provides expert guidance for Moon Dev's experimental AI trading ecosystem, a modular framework designed to manage a decentralized architecture of specialized agents. It enables developers to deploy, modify, and debug agents for risk management, sentiment analysis, and trade execution across platforms like Hyperliquid and Solana. By leveraging a unified ModelFactory for various LLMs and the Research-Based Inference (RBI) agent for automated backtesting, this skill serves as a comprehensive resource for building robust, AI-driven trading systems.

Características Principales

01Cross-Exchange Support: Native integration with Hyperliquid, Solana (BirdEye), and Extended Exchange.

02Modular Architecture: Lightweight, standalone agent design ensuring files remain under 800 lines for maintainability.

03Multi-Agent Orchestration: Manage 48+ specialized agents for risk, sentiment, and execution.

04LLM Abstraction: Unified ModelFactory interface supporting Claude, GPT-4, DeepSeek, and Groq.

0581 GitHub stars

06RBI Backtesting: Automatically convert trading ideas from videos or PDFs into executable backtest code.

Casos de Uso

01Developing autonomous AI-driven crypto trading strategies with integrated risk management circuit breakers.

02Creating custom market analysis tools that aggregate real-time sentiment, whale movements, and liquidation data.

03Backtesting trading logic derived from external research sources using the Research-Based Inference agent.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add microck/ordinary-claude-skills moon-dev-trading-agents

For use in Claude.ai and ChatGPT

Características Principales

01Cross-Exchange Support: Native integration with Hyperliquid, Solana (BirdEye), and Extended Exchange.

02Modular Architecture: Lightweight, standalone agent design ensuring files remain under 800 lines for maintainability.

03Multi-Agent Orchestration: Manage 48+ specialized agents for risk, sentiment, and execution.

04LLM Abstraction: Unified ModelFactory interface supporting Claude, GPT-4, DeepSeek, and Groq.

0581 GitHub stars

06RBI Backtesting: Automatically convert trading ideas from videos or PDFs into executable backtest code.

Casos de Uso

01Developing autonomous AI-driven crypto trading strategies with integrated risk management circuit breakers.

02Creating custom market analysis tools that aggregate real-time sentiment, whale movements, and liquidation data.

03Backtesting trading logic derived from external research sources using the Research-Based Inference agent.